Home · Business · Operations & Logistics · Quality control

PARTLY

As of 13 August 2026, AI can only partly check allergen information on your food labels.

This still needs a person who signs their name to it.

Can you do it?

5 minutesto a draft.

30 minutesto something you’d act on.

Cost, all in£0

Skill neededchat-fluent

Who has to check ita colleague

What the alternative costsNo priced alternative is listed in the supplied tool data.

If this goes wrong, an undeclared allergen can cause illness, a product withdrawal or a regulatory problem.

What to actually do

  1. Hand it to a person

    The route this page recommends

    A person who owns the outcome does this end to end, worth it when the failure is dear.

  2. Use a tool built for this

    Second choice
  3. Do it yourself

    The distant third

    A chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.

    How to actually do it

    1. Open the current approved recipe, product specification, supplier specifications and internal allergen matrix for the product.
    2. Photograph every relevant label panel in good light, including the ingredients list, allergen emphasis, precautionary wording, storage instructions and product name.
    3. Paste the approved documents into a chatbot and attach the label photographs using the prompt provided.
    4. Ask the model to produce its comparison table and separate confirmed matches from missing evidence, unreadable text and possible cross-contact issues.
    5. Compare every flagged ingredient and allergen against the current approved specification and supplier documents, not against the model's assumptions.
    6. Ask a competent quality or food safety colleague to resolve each discrepancy and record the evidence and decision in your quality-control system.
    7. Only release the label after the authorised person has approved the corrected artwork and retained the comparison record.

    Prompt

    Check the attached food label images against the approved product information below. Extract the label text exactly where possible, then produce a table with these columns: label wording, relevant ingredient or allergen, evidence in the approved specification, match status, and action needed. Check the current UK allergen requirements and the approved recipe, supplier specification and allergen matrix I provide, but do not rely on a guess or fill a gap from general knowledge. Flag unclear photographs, missing specifications, possible cross-contact, inconsistent precautionary wording, and any discrepancy between the label and the approved information. Do not approve the label for sale, give legal certainty, or invent an ingredient, allergen or supplier fact. End with a short list of questions a competent food safety or quality colleague must resolve before release.
    
    Label images:
    [ATTACH CLEAR PHOTOS OF EVERY RELEVANT LABEL PANEL]
    
    Approved recipe or product specification:
    [PASTE CURRENT APPROVED DOCUMENT]
    
    Supplier specifications and allergen information:
    [PASTE CURRENT SUPPLIER DOCUMENTS]
    
    Allergen matrix and internal labelling rules:
    [PASTE CURRENT INTERNAL DOCUMENTS]

    Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

What it gets wrong

  • AI cannot know whether the documents you supplied are current, complete or authorised.
  • AI cannot establish manufacturing cross-contact risks that are absent from the written specification.
  • AI cannot resolve ambiguous supplier wording or decide whether a precautionary statement is justified.
  • AI cannot take responsibility for releasing the label or for harm caused by an incorrect declaration.

What caps this at PARTLY: legal accountability, stakes of error and verification cost.

How we scored this

Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.

AxisScore (0–2)
Output2
Inputs2
Verification1
Liability0
Effort delta2
Total7 / 10

FAQ

Can ChatGPT check allergens on a food label?
It can read the label and compare its wording with the recipe, supplier specifications and allergen matrix you provide. It cannot prove that those documents are complete or approve the label for sale, so a competent quality colleague must make the release decision.
Can AI spot a missing allergen in an ingredients list?
It can flag a mismatch between visible ingredients and the approved product information. It may miss poor-quality text, hidden compound ingredients or cross-contact risks, so check every flag against the current controlled documents.
Is it safe to use AI for food allergen labelling?
Use it as a comparison and transcription aid, not as the final control. Your business remains accountable for the label, and a serious case needs a competent food safety or regulatory professional to assess the evidence.
What should I give AI to check a food label?
Give it clear photographs of every label panel, the current approved recipe or specification, supplier allergen documents and your internal allergen matrix. Remove unnecessary personal or confidential information, and mark any document whose currency or approval is uncertain.

Nearby answers

Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.

The newsletter

AI news, new answers and product picks, straight to your inbox.